arXiv subjects

Di Wu

Publications and source records attributed to Di Wu.

At least 559 records · Page 31Linked to original sources

arXiv2022

FedFly: Towards Migration in Edge-based Distributed Federated Learning

Federated learning (FL) is a privacy-preserving distributed machine learning technique that trains models while keeping all the original data generated on devices locally. Since devices may be resource constrained, offloading can be used to improve FL performance by transferring computational workload from devices to edge servers. However, due to mobility, devices participating in FL may leave the network during training and need to connect to a different edge server. This is challenging because the offloaded computations from edge server need to be migrated. In line with this assertion, we present FedFly, which is, to the best of our knowledge, the first work to migrate a deep neural network (DNN) when devices move between edge servers during FL training. Our empirical results on the CIFAR10 dataset, with both balanced and imbalanced data distribution, support our claims that FedFly can reduce training time by up to 33% when a device moves after 50% of the training is completed, and by up to 45% when 90% of the training is completed when compared to state-of-the-art offloading approach in FL. FedFly has negligible overhead of up to two seconds and does not compromise accuracy. Finally, we highlight a number of open research issues for further investigation. FedFly can be downloaded from https://github.com/qub-blesson/FedFly.

cs.DC↗

arXiv2022

WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model. To further improve ASR performance and facilitate various production requirements, in this paper, we present WeNet 2.0 with four important updates. (1) We propose U2++, a unified two-pass framework with bidirectional attention decoders, which includes the future contextual information by a right-to-left attention decoder to improve the representative ability of the shared encoder and the performance during the rescoring stage. (2) We introduce an n-gram based language model and a WFST-based decoder into WeNet 2.0, promoting the use of rich text data in production scenarios. (3) We design a unified contextual biasing framework, which leverages user-specific context (e.g., contact lists) to provide rapid adaptation ability for production and improves ASR accuracy in both with-LM and without-LM scenarios. (4) We design a unified IO to support large-scale data for effective model training. In summary, the brand-new WeNet 2.0 achieves up to 10\% relative recognition performance improvement over the original WeNet on various corpora and makes available several important production-oriented features.

cs.SD↗

arXiv2022

DeepC2: AI-powered Covert Command and Control on OSNs

Command and control (C&C) is important in an attack. It transfers commands from the attacker to the malware in the compromised hosts. Currently, some attackers use online social networks (OSNs) in C&C tasks. There are two main problems in the C&C on OSNs. First, the process for the malware to find the attacker is reversible. If the malware sample is analyzed by the defender, the attacker would be exposed before publishing the commands. Second, the commands in plain or encrypted form are regarded as abnormal contents by OSNs, which would raise anomalies and trigger restrictions on the attacker. The defender can limit the attacker once it is exposed. In this work, we propose DeepC2, an AI-powered C&C on OSNs, to solve these problems. For the reversible hard-coding, the malware finds the attacker using a neural network model. The attacker's avatars are converted into a batch of feature vectors, and the defender cannot recover the avatars in advance using the model and the feature vectors. To solve the abnormal contents on OSNs, hash collision and text data augmentation are used to embed commands into normal contents. The experiment on Twitter shows that command-embedded tweets can be generated efficiently. The malware can find the attacker covertly on OSNs. Security analysis shows it is hard to recover the attacker's identifiers in advance.

cs.CR↗

arXiv2022

Environment-Aware Hybrid Beamforming by Leveraging Channel Knowledge Map

Hybrid analog/digital beamforming is a promising technique to realize millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems cost-effectively. However, existing hybrid beamforming designs mainly rely on real-time channel training or beam sweeping to find the desired beams, which incurs prohibitive overhead due to a large number of antennas at both the transmitter and receiver with only limited radio frequency (RF) chains. To resolve this challenging issue, in this paper, we propose a new environment-aware hybrid beamforming technique that requires only light real-time training, by leveraging the useful tool of channel knowledge map (CKM) with the user's location information. CKM is a site-specific database, which offers location-specific channel-relevant information to facilitate or even obviate the acquisition of real-time channel state information (CSI). Two specific types of CKM are proposed in this paper for hybrid beamforming design in mmWave massive MIMO systems, namely channel angle map (CAM) and beam index map (BIM). It is shown that compared with existing environment-unaware schemes, the proposed environment-aware hybrid beamforming scheme based on CKM can drastically improve the effective communication rate, even under moderate user location errors, thanks to its great saving of the prohibitive real-time training overhead.

cs.IT↗

arXiv2022

Unconventional Excitonic States with Phonon Sidebands in Layered Silicon Diphosphide

Many-body interactions between quasiparticles (electrons, excitons, and phonons) have led to the emergence of new complex correlated states and are at the core of condensed matter physics and material science. In low-dimensional materials, unique electronic properties for these correlated states could significantly affect their optical properties. Herein, combining photoluminescence, optical reflection measurements and theoretical calculations, we demonstrate an unconventional excitonic state and its bound phonon sideband in layered silicon diphosphide (SiP$_2$), in which the bound electron-hole pair is composed of electrons confined within one-dimensional phosphorus$-$phosphorus chains and holes extended in two-dimensional SiP$_2$ layers. The excitonic state and the emergent phonon sideband show linear dichroism and large energy redshifts with increasing temperature. Within the $GW$ plus Bethe$-$Salpeter equation calculations and solving the generalized Holstein model non-perturbatively, we confirm that the observed sideband feature results from the correlated interaction between excitons and optical phonons. Such a layered material provides a new platform to study excitonic physics and many-particle effects.

cond-mat.mes-hall↗

arXiv2022

Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation

Objective. Deep neural networks (DNNs) have shown unprecedented success in various brain-machine interface applications such as epileptic seizure prediction. However, existing approaches typically train models in a patient-specific fashion due to the highly personalized characteristics of epileptic signals. Therefore, only a limited number of labeled recordings from each subject can be used for training. As a consequence, current DNN based methods demonstrate poor generalization ability to some extent due to the insufficiency of training data. On the other hand, patient-independent models attempt to utilize more patient data to train a universal model for all patients by pooling patient data together. Despite different techniques applied, results show that patient-independent models perform worse than patient-specific models due to high individual variation across patients. A substantial gap thus exists between patient-specific and patient-independent models. Approach. In this paper, we propose a novel training scheme based on knowledge distillation which makes use of a large amount of data from multiple subjects. It first distills informative features from signals of all available subjects with a pre-trained general model. A patient-specific model can then be obtained with the help of distilled knowledge and additional personalized data. Main results. Four state-of-the-art seizure prediction methods are trained on the Children's Hospital of Boston-MIT sEEG database with our proposed scheme. The resulting accuracy, sensitivity, and false prediction rate show that our proposed training scheme consistently improves the prediction performance of state-of-the-art methods by a large margin. Significance. The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.

cs.LG↗

arXiv2022

HIFI-Net: A Novel Network for Enhancement to Underwater Images

A novel network for enhancement to underwater images is proposed in this paper. It contains a Reinforcement Fusion Module for Haar wavelet images (RFM-Haar) based on Reinforcement Fusion Unit (RFU), which is used to fuse an original image and some important information within it. Fusion is achieved for better enhancement. As this network make "Haar Images into Fusion Images", it is called HIFI-Net. The experimental results show the proposed HIFI-Net performs best among many state-of-the-art methods on three datasets at three normal metrics and a new metric.

cs.CV↗

arXiv2022

C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

Recent development in brain-machine interface technology has made seizure prediction possible. However, the communication of large volume of electrophysiological signals between sensors and processing apparatus and related computation become two major bottlenecks for seizure prediction systems due to the constrained bandwidth and limited computation resource, especially for wearable and implantable medical devices. Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction. In this paper, we propose C$^2$SP-Net, to jointly solve compression, prediction, and reconstruction with a single neural network. A plug-and-play in-sensor compression matrix is constructed to reduce transmission bandwidth requirement. The compressed signal can be used for seizure prediction without additional reconstruction steps. Reconstruction of the original signal can also be carried out in high fidelity. Prediction accuracy, sensitivity, false prediction rate, and reconstruction quality of the proposed framework are evaluated under various compression ratios. The experimental results illustrate that our model outperforms the competitive state-of-the-art baselines by a large margin in prediction accuracy. In particular, our proposed method produces an average loss of 0.35 % in prediction accuracy with a compression ratio ranging from 1/2 to 1/16.

cs.LG↗

arXiv2022

Consistent mass formulas for the four-dimensional dyonic NUT-charged spacetimes

In our previous work, a novel idea that the NUT charge can be thought of as a thermodynamical multi-hair has been advocated to describe perfectly the thermodynamical character of the generic four-dimensional Taub-NUT spacetimes. According to this scheme, the Komar mass M, the gravito-magnetic charge and/or the dual (magnetic) mass N, together with a new secondary hair J_N=MN, namely, a Kerr-like conserved angular momentum, enter into the standard forms of the first law and Bekenstein-Smarr mass formula. Distinguished from other recent attempts, our consistent thermodynamic differential and integral mass formulae are both obtainable from a meaningful Christodoulou-Ruffini-type squared mass formula of almost all of the four-dimensional NUT-charged spacetimes. As an excellent consequence, the famous Bekenstein-Hawking one-quarter area-entropy relation can be naturally restored not only in the Lorentzian sector and but also in the Euclidian counterpart of the generic Taub-NUT-type spacetimes without imposing any constraint condition. However, only purely electric-charged cases in the four-dimensional Einstein-Maxwell gravity theory with a NUT charge have been addressed there. In this paper, we shall follow the simple, systematic way proposed in that article to further investigate the dyonic NUT-charged case. It is shown that the standard thermodynamic relations continue to hold true provided that no new secondary charge is added, however, the so-obtained electrostatic and magneto-static potentials are not coincident with those computed via the standard method. To rectify this inconsistence, a simple strategy is provided by further introducing two additional secondary hairs: Q_N=QN and P_N=PN, together with their thermodynamical conjugate potentials, so that the first law and Bekenstein-Smarr mass formula are still satisfied.

gr-qc↗

arXiv2022

Hunting for extra dimensions in the shadow of Sagittarius A*

Recently, Vagnozzi and Visinelli's work [Phys. Rev. D 100, 024020 (2020)] reveals that M87*'s shadow establishes an upper limit of $l \lesssim 170$ AU, where $l$ is the AdS$_5$ curvature radius and 1 AU is one astronomical unit. The Event Horizon Telescope, on the other hand, just captured the first image of the shadow of Sagittarius A* (SgrA*), the Galactic center source associated with a supermassive black hole. In this paper, we are motivated to comprehensively explore a new upper limit of $l$ with the shadow of SgrA*, and the findings suggest that $l \lesssim 0.097$ AU. Our results improve accuracy by three orders of magnitude. This is also one of the first quantifiable limitations on exotic physics derived from the remarkable first image of the shadow of SgrA*.

gr-qc↗

arXiv2022

Differentially Private AUC Computation in Vertical Federated Learning

Federated learning has gained great attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple parties. As a sub-category, vertical federated learning (vFL) focuses on the scenario where features and labels are split into different parties. The prior work on vFL has mostly studied how to protect label privacy during model training. However, model evaluation in vFL might also lead to potential leakage of private label information. One mitigation strategy is to apply label differential privacy (DP) but it gives bad estimations of the true (non-private) metrics. In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL. Through extensive experiments, we show our algorithms can achieve more accurate AUCs compared to the baselines.

cs.LG↗

arXiv2022

FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning

Applying Federated Learning (FL) on Internet-of-Things devices is necessitated by the large volumes of data they produce and growing concerns of data privacy. However, there are three challenges that need to be addressed to make FL efficient: (i) execution on devices with limited computational capabilities, (ii) accounting for stragglers due to computational heterogeneity of devices, and (iii) adaptation to the changing network bandwidths. This paper presents FedAdapt, an adaptive offloading FL framework to mitigate the aforementioned challenges. FedAdapt accelerates local training in computationally constrained devices by leveraging layer offloading of deep neural networks (DNNs) to servers. Further, FedAdapt adopts reinforcement learning based optimization and clustering to adaptively identify which layers of the DNN should be offloaded for each individual device on to a server to tackle the challenges of computational heterogeneity and changing network bandwidth. Experimental studies are carried out on a lab-based testbed and it is demonstrated that by offloading a DNN from the device to the server FedAdapt reduces the training time of a typical IoT device by over half compared to classic FL. The training time of extreme stragglers and the overall training time can be reduced by up to 57%. Furthermore, with changing network bandwidth, FedAdapt is demonstrated to reduce the training time by up to 40% when compared to classic FL, without sacrificing accuracy.

cs.DC↗

arXiv2022

MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning

Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on sophisticated translation models. In this study, we propose a super lightweight unsupervised word alignment model named MirrorAlign, in which bidirectional symmetric attention trained with a contrastive learning objective is introduced, and an agreement loss is employed to bind the attention maps, such that the alignments follow mirror-like symmetry hypothesis. Experimental results on several public benchmarks demonstrate that our model achieves competitive, if not better, performance compared to the state of the art in word alignment while significantly reducing the training and decoding time on average. Further ablation analysis and case studies show the superiority of our proposed MirrorAlign. Notably, we recognize our model as a pioneer attempt to unify bilingual word embedding and word alignments. Encouragingly, our approach achieves {16.4X speedup} against GIZA++, and {50X parameter compression} compared with the Transformer-based alignment methods. We release our code to facilitate the community: https://github.com/moore3930/MirrorAlign.

cs.CL↗

arXiv2022

Constrained Adaptive Projection with Pretrained Features for Anomaly Detection

Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning on one-class training data. In this paper, we propose an anomaly detection framework called constrained adaptive projection with pretrained features (CAP). Combined with pretrained features, a simple linear projection head applied on a specific input and its k most similar pretrained normal representations is designed for feature adaptation, and a reformed self-attention is leveraged to mine the inner-relationship among one-class semantic features. A loss function is proposed to avoid potential pattern collapse. Concretely, it considers the similarity between a specific data and its corresponding adaptive normal representation, and incorporates a constraint term slightly aligning pretrained and adaptive spaces. Our method achieves state-ofthe-art anomaly detection performance on semantic anomaly detection and sensory anomaly detection benchmarks including 96.5% AUROC on CIFAR- 100 dataset, 97.0% AUROC on CIFAR-10 dataset and 89.9% AUROC on MvTec dataset.

cs.CV↗

arXiv2022

Magnetic phase transition induced ferroelectric polarization in BaFeF4 with room temperature weak ferromagnetism

BaMF4 (M=Fe, Co, Ni and Mn) family are typical multiferroic materials, having antiferromagnetism at around liquid nitrogen temperature. In this work, polycrystalline BaFeF4 has been prepared by solid state reaction. The slight deficiency of Fe leads to the coexistence of valence states of +2 and +3, facilitating the electrons to hop between the neighboring Fe2+ and Fe3+ ions through the middle F- ion, leading to the strong double exchange interaction with weak ferromagnetism above room temperature. A bifurcation at about 170 K between the zero-field-cooled and field-cooled temperature dependent magnetization curves indicates the onset of 2-dimensional antiferromagnetism, which is completed at about 125 K with the sudden drop of magnetization. Despite the fact of type-I multiferroic, its magnetoelectricity can be evidenced by the pyroelectric current, which shows a peak starting at about 170 K and finishing at about 125 K. The saturated ferroelectric polarization change of around 34 μC/m2 is observed, which is switchable by the reversed poling electric field and decreases to about 30 μC/m2 under a magnetic field of 90 kOe. This magnetoelectricity can be qualitatively reproduced by first-principles calculations. Our results represent substantial progress to search for high-temperature multiferroics in ferroelectric fluorides.

cond-mat.mtrl-sci↗

arXiv2022

A Differential Evolution-Enhanced Latent Factor Analysis Model for High-dimensional and Sparse Data

High-dimensional and sparse (HiDS) matrices are frequently adopted to describe the complex relationships in various big data-related systems and applications. A Position-transitional Latent Factor Analysis (PLFA) model can accurately and efficiently represent an HiDS matrix. However, its involved latent factors are optimized by stochastic gradient descent with the specific gradient direction step-by-step, which may cause a suboptimal solution. To address this issue, this paper proposes a Sequential-Group-Differential- Evolution (SGDE) algorithm to refine the latent factors optimized by a PLFA model, thereby achieving a highly-accurate SGDE-PLFA model to HiDS matrices. As demonstrated by the experiments on four HiDS matrices, a SGDE-PLFA model outperforms the state-of-the-art models.

cs.LG↗

arXiv2022

Graph-incorporated Latent Factor Analysis for High-dimensional and Sparse Matrices

A High-dimensional and sparse (HiDS) matrix is frequently encountered in a big data-related application like an e-commerce system or a social network services system. To perform highly accurate representation learning on it is of great significance owing to the great desire of extracting latent knowledge and patterns from it. Latent factor analysis (LFA), which represents an HiDS matrix by learning the low-rank embeddings based on its observed entries only, is one of the most effective and efficient approaches to this issue. However, most existing LFA-based models perform such embeddings on a HiDS matrix directly without exploiting its hidden graph structures, thereby resulting in accuracy loss. To address this issue, this paper proposes a graph-incorporated latent factor analysis (GLFA) model. It adopts two-fold ideas: 1) a graph is constructed for identifying the hidden high-order interaction (HOI) among nodes described by an HiDS matrix, and 2) a recurrent LFA structure is carefully designed with the incorporation of HOI, thereby improving the representa-tion learning ability of a resultant model. Experimental results on three real-world datasets demonstrate that GLFA outperforms six state-of-the-art models in predicting the missing data of an HiDS matrix, which evidently supports its strong representation learning ability to HiDS data.

cs.LG↗

arXiv2022

A Multi-Metric Latent Factor Model for Analyzing High-Dimensional and Sparse data

High-dimensional and sparse (HiDS) matrices are omnipresent in a variety of big data-related applications. Latent factor analysis (LFA) is a typical representation learning method that extracts useful yet latent knowledge from HiDS matrices via low-rank approximation. Current LFA-based models mainly focus on a single-metric representation, where the representation strategy designed for the approximation Loss function, is fixed and exclusive. However, real-world HiDS matrices are commonly heterogeneous and inclusive and have diverse underlying patterns, such that a single-metric representation is most likely to yield inferior performance. Motivated by this, we in this paper propose a multi-metric latent factor (MMLF) model. Its main idea is two-fold: 1) two vector spaces and three Lp-norms are simultaneously employed to develop six variants of LFA model, each of which resides in a unique metric representation space, and 2) all the variants are ensembled with a tailored, self-adaptive weighting strategy. As such, our proposed MMLF enjoys the merits originated from a set of disparate metric spaces all at once, achieving the comprehensive and unbiased representation of HiDS matrices. Theoretical study guarantees that MMLF attains a performance gain. Extensive experiments on eight real-world HiDS datasets, spanning a wide range of industrial and science domains, verify that our MMLF significantly outperforms ten state-of-the-art, shallow and deep counterparts.

cs.LG↗